Analyzing Online Customer Reviews for the Hotel Classification in Vietnam
←
→
Page content transcription
If your browser does not render page correctly, please read the page content below
Ha Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451 443
Print ISSN: 2288-4637 / Online ISSN 2288-4645
doi:10.13106/jafeb.2021.vol8.no8.0443
Analyzing Online Customer Reviews for the
Hotel Classification in Vietnam
Ha Thi Thu NGUYEN1, Tuan Minh TRAN2, Giang Binh NGUYEN3
Received: April 20, 2021 Revised: July 04, 2021 Accepted: July 15, 2021
Abstract
The classification standards for hotels in Vietnam are different from many other hotel classification standards in the world. This study
aims to analyze customer reviews on the TripAdvisor website to develop a new algorithm for hotel rating that is independent of Vietnam’s
hotel classification standards. This method can be applied to individual hotels, or hotels of a region or the whole country, while online
booking sites only rate individual hotels. Data was crawled from TripAdvisor with 22,287 reviews of 5 cities in Vietnam. This study used
a statistical model to analyze the review dataset and build an algorithm to rate hotels according to aspects or hotel overall. The results
have less rating deviation when compared to the TripAdvisor system. This study also supports hotel managers to regularly update the
status of their hotels using data from customer reviews, from which, managers can strategize long-term solutions to improve the quality
of the hotel in all aspects and attract more travelers to Vietnam. Moreover, this method can be developed into an automatic system to rate
hotels and update the status of service quality more quickly, thus, saving time and costs.
Keywords: Hotel Management, Customer’s Review, Vietnamese Hotel, Aspect Rating, Overall Rating
JEL Classification Code: C10, C40, C82, M15, P21, P25
1. Introduction tourism has changed, the quality and service also changed
according to the opinions and evaluations of guests instead
Hotel ratings are often used to classify hotels according of the criteria developed by organizations. Many hotel
to their quality. From the initial purpose of informing classification organizations update their criteria according
travelers on basic facilities that can be expected, the to guest preferences and needs when mining guest opinion
objectives of hotel rating have expanded into a focus on (Rhee & Yang 2015; Xue et al., 2017).
the hotel experience as a whole (Le et al., 2020). Currently, The hotel industry is a competitive market where
hotel rating has become one of the important factors to hotels are continuously trying to improve their service
promote a hotel brand to affirm its position. There are a quality to satisfy customers because higher customer
number of hotel classification organizations in the world. satisfaction will lead to customer loyalty and increase
Each organization develops its own criteria for hotel the return rate of guests. Online booking systems help
classification. In recent years, the strong development to promote the hotel’s brand and reputation better than
of online hotel booking systems shows that the trend of traditional business but it increases competition among
hotels (Kim et al., 2021). Ratings by hotel classification
organizations are not of much significance because
First Author and Corresponding Author. Lecturer, Department of
1
travelers now tend to trust the reviews of travelers who
Ecommerce, Electric Power University, Vietnam [Postal Address: have experienced the same service. Therefore, today, the
235 Hoang Quoc Viet St., Bac Tu Liem Dist., Hanoi City, 10000,
Vietnam] Email: hantt@epu.edu.vn opinions/reviews of travelers have more weight than any
Associate Professor of Economics, Vietnam Academy of Social
2
other standard. When selecting hotels, travelers rely on
Sciences, Vietnam. Email: minhtuanvass@gmail.com the number of positive reviews. Travelers selecting hotels
Lecturer, Vietnam Academy of Social Sciences, Vietnam.
3
Email: ng.binh.giang@gmail.com base their decisions on online reviews. TripAdvisor is
a hotel rating system based on the reviews of travelers/
© Copyright: The Author(s)
This is an Open Access article distributed under the terms of the Creative Commons Attribution customers who have stayed in that hotel and experienced
Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits
unrestricted non-commercial use, distribution, and reproduction in any medium, provided the
their service. As for the TripAdvisor rating system,
original work is properly cited. a review of a hotel furnishes information on the quality444 Ha Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451
of accommodation, restaurant, and on-site spots worth aims to achieve the following main objectives: (1) Improving
visit. TripAdvisor uses an online scoring method on the the quality of guest service, and ensuring the interests of
website system for hotels across the globe the world. tourists so as to attract tourists; (2) As a standard for building
TripAdvisor star rating is based on third-party users with hotels, (3) The standard of providing service to ensure the
respect to the quality of services – staff quality, quality consistency of service quality between types of hotels in
of the amenities available. It provides full data such as each country and between the nations; (4) Evaluating and
hotel overall rating, list of reviews, hotel aspects rating, measuring the quality of the hotel; (5) Determining service
and hotel ranking. Online hotel rating has now become prices and have appropriate pricing policies for each hotel
a new criterion that hotel managers pursue because of segment within the global market (Abrate et al., 2021;
its usefulness and convenience (Wang et al., 2019; Sánchez-Lozano et al., 2021).
Le et al., 2020): There are many different hotel classification standards
in the world. HOTREC is the umbrella association of hotels,
• T
he standard rating is based on the traveler’s opinion. restaurants, pubs, cafes, and similar establishments in Europe,
• T
he price is equivalent among the same level hotels. and is the voice of the hospitality industry in Europe. Since
• M
easuring the quality of hotel service based on 2004, HOTREC and its associations have been working
travelers’ reviews will help to better understand on bringing the hotel classification systems in the various
travelers’ need. European countries closer to one another. Under the auspices
• H
elp travelers make decisions faster when they book of HOTREC, hotel associations of Austria, Czech Republic,
online. Germany, Hungary, the Netherlands, Sweden, and Switzerland
founded the Hotelstars Union as a common standard for rating
The first behavior of a traveler when booking online hotels in Europe (https://www.hotelstars.eu/criteria/). Hotels
is to look at the number of stars assigned to the hotel, and in the UK star ratings are awarded and managed by four Hotel
second, they tend to read the reviews related to that hotel rating boards: The AA, Visit Britain, Visit Scotland, and Visit
(Masiero & Nicolau 2016; El-Said 2020; Goeltom et al. Wales (https://www.theaa.com/). The standard of a 5-star hotel
2020). Star ratings are indicators used to classify hotels in the UK requires hotels to have among others a spa, fitness
according to their quality. For customers, they can lead the center, butler service, valet parking, reception, afternoon
decision-making process; for staff, they can help to define tea, and 24/7 room service. Australia is one of the countries
best practices and guidelines, as well as helping to attract with the strictest hotel classification standards in the world.
customers in a competitive market. Online hotel rating Therefore, Australia now has only thirty-nine 5-star hotels.
systems such as TripAdvisor rate only individual hotels With more than 200 different criteria to compare, evaluate
(De Pelsmacker et al., 2018). Therefore, the tourism and score (room size, opening hours, etc.) it is not easy for
managers do not have a general overview of the hotels of a hotels in Australia to achieve a high star rating. In the US,
region or the whole country. hotel classification standards focus on quality bedrooms. This
Tourism has become one of the major sectors within is one of the top criteria for a hotel rating. In addition, a 5-star
the economy of Vietnam in recent years. Vietnam is the hotel must also have services such as alarm service, luxury
only Southeast Asian country among 10 world’s fastest- spas, golf courses, tennis courts, personal trainers, etc. or even
growing travel destinations. The classification standard babysitting services.
system of Vietnamese hotels is approved by the Ministry In Vietnam, hotels are classified by National Standard
of Science and Technology since 2015, however, the TCVN 4391: 2009 (Vietnam Directorate for Standards,
classification standards are not in line with today’s online Metrology, and Quality, https://tcvn.gov.vn). Hotels are rated
travel trends. In this study, a new Vietnamese hotel rating according to location, architecture, equipment and service
method is proposed, which will help managers in the facilities, service quality and service level, staff, cleanness,
Vietnam Ministerial and Department of Culture, Sport and room availability and standards, etc. Hotels from 1 to 5
Tourism have a detailed rating system of Vietnamese hotels stars are hotels with high-quality facilities, equipment, and
based on all the aspects of the hotel, and overall, can be services, meeting the diverse needs of guests’ requirements
applied to hotels in a region or for the whole of Vietnam, such as food, accommodation, activities, and entertainment
respectively (https://vietnamtourism.gov.vn ). according to international standards.
2. Literature Review 2.2. Hotel Star Rating from Analyzing
Online Review
2.1. Hotel Classification System
Data is everywhere and it is revolutionizing the field
Hotel classification plays an important role in develop of statistics radically (Lee 2020; Park & Javed 2020).
ing the tourism and hospitality industry. Hotel classification Undeniably big data has huge potential for many fieldsHa Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451 445
of statistics. The emergence of big data is also changing the Few studies on hotel ratings used unsupervised
working environment of statisticians. Ignoring innovation learning. Akhtar et al. (2017) analyzed hotel reviews and
will push statistical agencies out of the information market gave information that ratings might overlook. The reviews
(Kim & Yoo 2021). Tourism boards and companies in the and metadata are crawled from the website and classified
tourism sector can benefit from data of this type in many into predefined classes as per some of the common
ways. Players in the tourism industry can now make informed aspects. Then the Topic modeling technique (LDA)
decisions based on analytics and number-driven data. They is applied to identify hidden information and aspects,
can identify targeted groups of potential customers at every followed by sentiment analysis on classified sentences and
stage in the trip planning process. They can also increase summarization. Wang et al. (2010) defined and studied a
efficiency and the quality of services (Jeon et al., 2019). new opinionated text data analysis problem called Latent
Online travelers tend to trust reviews of customer Aspect Rating Analysis (LARA), which aimed at analyzing
experience more than hotel advertisements. This online opinions expressed about an entity in an online review at
review data over the years become big data and is readily the level of topical aspects to discover each individual
available for anyone to tap into. Big data analysis using reviewer’s latent opinion on each aspect as well as the
artificial intelligence tools and models was suggested to relative emphasis on different aspects when forming the
match the tasks and challenges of big data (Park & Javed overall judgment of the entity.
2020; Luo & Tang 2019; Manes & Tchetchik 2018; Chang Sharma et al. (2019) proposed a hotel ranking model
et al., 2019). TripAdvisor uses data of online guest reviews based on the aspect ratings accessed from Tripadvisor
to rate hotels. Officially, TripAdvisor follows bubble rating website. The aspects play the role of criteria consisting of
and star rating. TripAdvisor bubble rating is indicative of service, cleanliness, value, sleep quality, room, and location.
the summary of user reviews. Thus, it indicates real reviews These ratings are classified into positive, neutral, and
by real people at a point in time. The TripAdvisor bubble negative sentiments, which are transformed to Neutrosophic
rating is a 1 to 5 scale. TripAdvisor star rating is based on numbers and results in the formation of interval-valued
third-party users with respect to the quality of services – Neutrosophic decision matrix. Also, since the aspect weights
staff quality, quality of the amenities available (Al-Natour & are completely unknown, a non-linear programming model
Turetken 2020; Bigné et al., 2020). called maximizing deviation method is employed. Last,
There are many studies on opinion and aspect ratings for the aspect weights and decision matrix are combined to
products, but hotel ratings have a few studies mentioned. perform the procedure required for applying technique for
The rating problem usually has two main approaches, one order preferences by similarity to ideal solution method for
is based on supervised learning and the other is based on ranking five alternative hotels.
unsupervised (Sokhin et al., 2020; Lai & Hsu 2021). While Luo and Tang (2019) modified the Latent Aspect Rating
supervised methods achieve high scores, it is hard to use Analysis (LARA) to achieve this research objective. They
them in real-world applications due to the lack of labeled identified five aspects; communication, experience, location,
datasets. For aspect ratings, unsupervised learning is more product/service, and value. Joy and surprise are the primary
effective because travelers often score overall and do not emotions shown in textual reviews. This study provided an
score aspects (Hu et al., 2016). Aspects are only mentioned innovative research venue for incorporating both textual
in reviews, however, customers actually choose products reviews and numerical ratings into the assessment. Xue
based on their interests, such as color, function, services, etc. et al. (2017) proposed two topic models which explicitly
Studies in the field of aspect rating focus on analyzing model aspect ratings as observed variables to improve the
customer evaluation data using unsupervised learning. performance of aspect rating inference on unrated reviews.
Lai and Hsu (2021) proposed aspect-based rating The experiment results showed that their approaches
prediction methods, which integrate aspect detection and outperform the existing methods on the data set crawled
sentiment analysis to generate user preference and business from the TripAdvisor website.
performance, combined with the results of social behavior In this study, the authors used text analysis techniques to
analysis to predict the ratings of the businesses that users rate hotels according to the hotel’s aspect and a deep layer
will be interested in the future. Margaris and Vassilakis neural network model to rate the hotels overall with real
(2018) used a methodology of dynamic average computing data of Vietnamese hotels that is taken from TripAdvisor.
based on previous ratings; this method can improve the The low error shows that the proposed model is really
accuracy of results. Sokhin et al. (2020) presented a novel effective and applied in practice in the star rating of hotels
unsupervised neural network with a convolutional multi- in Vietnam. This research with Vietnamese hotels’ real data
attention mechanism, that allows extracting pairs (aspect, has implications for hotel management and describes the
term) simultaneously, and demonstrates the effectiveness on current situation, hence, can be a suggestion in updating the
the real-world dataset. current Vietnamese hotel classification standards.446 Ha Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451
3. Research Methods and Materials efinition 4. Overall rating
• D
The overall rating is a measure of the overall quality of
3.1. Problem Definition the hotel’s services and is assigned a score from 1star
to 5 stars.
In this study, both overall rating and aspect rating
methods are proposed. Figure 1 below depicts the data efinition 5. Aspect rating
• D
collection process and hotel star rating based on big data Aspect rating is a measure of the quality of each
analysis. service in a hotel and is assigned a score from 1star to
In this study, a number of definitions are used as follows: 5 stars. For example, Room is rated 3 stars, Location
is rated 2 stars
• D
efinition 1. Reviews of guests
Reviews of guests are comments about the hotel that efinition 6. Region rating
• D
are written by guests who have experience, and is Region rating is a measure of the quality of each
expressed as: service or overall service of all hotels in a region
and classified according to the star level from 1–5.
{r1 , r2 , , rn } (1)
For example, Hotels in Danang city with an overall
rating of 3.7 stars and hotels in Nhatrang city with an
• D
efinition 2. Aspects of a hotel overall rating of 4.2 stars.
Aspects of a hotel are the attributes of the hotel, and
the services provided to guests by the hotel, and is efinition 7. Hotel ranking
• D
expressed as: Hotel ranking is its rank in the list of hotels in
Vietnam or a certain region. For example, Lotte
A = {a1 , a2 , , am } (2) Hanoi Hotel is number #6 in the list of hotels in the
Hanoi capital.
• D
efinition 3. Rating of hotel
Rating is the classification of the hotel into five efinition 8. Sentiment words
• D
different star levels, starting from 1 star to 5 stars. Sentiment words are the set of adverbs and adjectives
that are extracted from reviews (ℜ).
______
W {wi , i 1 k , wi is adverb or adjective} (3)
• D
efinition 9. Aspect grouping
Aspect grouping is a set of words with the same
meaning.
a1 = {a11 , a12 , , a1m } (4)
For example:
Aspect price = {value, price}
Aspect location = {location, place}
3.2. Aspect Rating Based on Big Data Analysis
Hotel rating by aspects is difficult because most travelers
only give stars for overall quality/level and write reviews.
A few travelers make detailed reviews by aspects or give
star ratings for different aspects. Therefore, when star rating
by aspect, it is more appropriate to use rating-based scoring
methods than supervised learning methods. This research is
Figure 1: Hotel Star Rating Process conducted in two phases, six steps.Ha Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451 447
hase 1: Calculating sentiment value of adjectives and
• P
adverbs Aspect
Step 1: Building a dataset Room Location Services Staff
Reviews are collected and pre-processed, and Sentiwords
then segmented into sentences
Great 10.8 4.98 4.02 7.44
Step 2: Classifying sentences
Sentences are classified into positive or Large 6.6 0.4 0 0
negative sentences Near 4.8 42.24 0 0
Step 3: Calculating the weight of sentiment words …. …. …. … …
Using sentiment lexicon for extracting adjectives
Bad 2.04 0.69 2.91 1.98
and adverbs, score them by the equation:
Weight(wi) = pos(si) + neg(si) The Value of each cell is the value calculated by:
In which: weight (great) × co−occur(great, room)
number of occurences of si And the weight of the aspect ‘room’ is calculated as:
in the positive sentences
pos( si ) = (5) Weight (room) = w
eight (great) × co−occur (great, room)
total of sentences in dataset
+ weight (large) × co−occur
number of occurences of si (larger, room) × weight (near)
× co−occur (near, room) × … × weight
in the negative sentences (bad) × co−occur (bad, room)
neg ( si ) = (6)
total of sentences in dataset
Aspect Weight Aspect Rating
• P
hase 2: Aspect rating
Step 4: Aspect identification: Room 24.24 2.5
Using aspect grouping to extract aspects from Location 48.31 5
a dataset. Service 6.93 1
Step 5: Calculating the weight of aspects:
Staff 9.42 1
Weight of an aspect is the product of the total
sum of co-occurrence of aspect ai with each senti
ment word wj and weight of sentiment word wj. 3.3. Hotel Overall Rating
Weight (ai ) j 1 w j co occur ( w j , ai ) (7)
m The overall star rating of the hotel allows travelers to
know about the quality of the whole service not only each
aspect. The overall star rating of a hotel is calculated as the
In which: average of the aspect rating
Weight(ai): Weigh of aspect ith
wj: Weight of sentiment word jth
m
(rating (a j ))
co−occur(wj , ai): Number of co-occurrence of aspect ith Rating(hotel k ) j 1
(9)
and sentiment word jth m
Step 6: Aspect rating
Aspects are rated by the equation below: In which Rating(hotelk) is the rating of hotel k and m is
the total of aspects of hotel k.
Value(ai ) The overall star rating for hotels in a region is calculated
Rating (ai ) 5 (8) as the average of the overall ratings of hotels in this region:
arg max (Value(a ))
n
(rating(hotel k ))
Rating(ai) is fixed by 1 when the result ⇐ 1. Rating (region )
s
k 1
(10)
Example: n
Suppose that we have a value matrix, one dimension
is aspects and the other is sentiment words in the In which Rating(regions) is the rating of region s and n is
sentiment set. the number of hotels in region s.448 Ha Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451
4. Results 4.2. Hotel Aspect Rating
4.1. Data Most travelers use star ratings for overall service, so
aspect rating is done by using an unsupervised learning
In this study, the data was collected from the method (without labeled data). Because previous studies
world’s most famous travel site, TripAdvisor. TripAdvisor have not been conducted with Vietnamese hotel data, this
uses an efficient rating algorithm and is always study uses some of the aspects that are rated by TripAdvisor
updated in real-time. In addition, TripAdvisor also warns such as Location, Cleanliness, Services, and Value. Other
when it detects fraud from hotel managers for increasing aspects are not used for comparison.
Internet rankings. The authors used a tool to crawl guest The deviation is calculated by the formula:
reviews of Vietnamese hotels from 4 to 5 stars. The dataset
is saved as a .csv file with the information: reviewer (rating _ a (hotel k )
c
name, review content, date of stay, and the number of Deviation_aspect TRIPrating _ a (hotel k )) (11)
k 1
review stars. The number of reviews includes 22,287
(a) c
online reviews taken from the TripAdvisor website with
12 hotels from 4 stars to 5 stars in 04 cities in Vietnam 100%
including Hanoi, Ho Chi Minh City, Nha Trang, Danang
(Table 1). In which Deviation_aspect(a) is the difference between
The data is pre-processed as follows: this study’s rating and TripAdvisor rating of aspect a;
rating_a(hotelk) is the rating of aspect a for hotel k by the
• Travelers wrote reviews but do not give the hotel study method and TRIPrating_a(hotelk) is the rating of
star rating, then these reviews are removed from aspect a for hotel k by TripAdvisor.
the list. Results for 12 hotels in Vietnam with an average deviation
• Travelers wrote reviews with symbols likeHa Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451 449
database of the website http://vietnamhotel.org.vn and the tourists in Southeast Asia and the top 10 most attractive
hotel star rating of the TripAdvisor site. The simple deviation destinations in the world. Tourism has become one of the
comparison uses the following formula major sectors within the economy of Vietnam in recent years,
with a direct GDP contribution of over nine percent in 2019.
(standard _ RATED(hotel k ) In the same year, Vietnam also welcomed a record-high
c
Deviation k 1
RATED(hotel k )) number of international visitor arrivals. The contribution of
(12) accommodation services to the tourism industry accounts for
(hotelin VN) c more than 70%, which shows the importance of the tourism
100% sector which includes the hotel industry for the country’s
economic development.
Standard_RATED(hotelk) is the national standard rating To continue to attract tourists, especially international
of hotel k. c is the total number of hotels. The resulting tourists, the quality of services needs to be upgraded in
deviation for 12 hotels is 56.4%. This value shows that line with guest requirements and global standards. Hotel
online guests rated lower than Vietnamese standards. The classification organizations have considered online ratings
difference is about 0.5 stars. The table below shows the as a suitable criterion for updating rating standards over
difference between the actual rating and the rating on the time in order to rank hotels accordingly. However, it is also
TripAdvisor site and the analysis method of the study for a not possible to update faster than online rating because
number of hotels in Vietnam (Table 3). these systems work with huge amounts of data and always
The results on the table show that the rating according to adjust ratings in real-time. Therefore, hotel classification
this method and the rating on the TripAdvisor site has less organizations must always update the rating criteria as well
difference than the difference between the national standard as update the current status of hotel ratings in the latest way.
rating and the rating on the TripAdvisor site. For Vietnam, hotel management focuses mainly on
quality management in hotels and hotel promotion to attract
6. Discussion and Conclusion tourists. Therefore, the hotel rating is meant to affirm
the quality of the hotel and the quality commitment that
The trend of booking tours is growing and the number guests can enjoy when using the hotel services. Moreover,
of travelers booking through online channels is increasing the rating system indicates the prestige and reputation of
rapidly, showing the fierce competition between hotels and hotels as well as the hotel classification system in Vietnam.
tourist destinations. Vietnam is a country rated by tourism Therefore, online star ratings for Vietnamese hotels can
organizations as the 3rd most attractive destination for help hotel managers:
Table 2: Comparing Aspect Rating Results with TripAdvisor • A
djust criteria in the national standard system to
match and harmonize with the user’s online star rating
Aspect Deviation standard and asymptote (get closer and closer to) with
the world’s set of star rating standards to gradually
Location 0.32
unify by global standards.
Cleanliness 0.47 • R
educe unnecessary procedures, reduce processing
Service 0.525 time and reduce the cost of star level updating for
Value 0.2 hotels by Vietnam hotel classification organization.
Gradually approach the one-stop electronic adminis
Average of all aspect 0.37875 trative process and return results more quickly.
Table 3: The Result of the Difference Between the Standard Rating, the Study Method, and the TripAdvisor Rating
Rated by Vietnam National
Name of Hotel Rated by Our Method Rated by TripAdvisor
Administration of Tourism
Fortuna Hotel 4 4.2 4
Hanoi Lotte Hotel 5 4.7 5
BaoSon Hotel 4 3.6 3.5
Intercontinental NhaTrang 5 4.2 5
Rex Hotel 5 4.8 4450 Ha Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451
• I t is possible to build an automatic system for hotel role of consumer satisfaction as mediator. Journal of Asian
classification by the process applied in this study. This Finance, Economics, and Business, 7(11), 967–976. https://doi.
way, hotels can easily manage and strictly control the org/10.13106/jafeb.2020.vol7.no11.967
quality of service of the hotel. Hu, H. W., Chen, Y. L., & Hsu, P. T. (2016). A novel approach
• H otel classification according to the world’s general to rate and summarize online reviews according to user-
standards is also the basis for building a price suitable specified aspects. Journal of Electronic Commerce
for Vietnamese hotels with international standards. Research, 17(2), 132–152. http://www.jecr.org/sites/default/
• U nderstand the real needs and opinions of tourists as files/17_2Paper3.pdf
well as the actual quality of the hotel so that hotels Jeon, S. W., Lee, H. J., Lee, H., & Cho, S. (2019). Graph-based
can improve and enhance their quality to attract more aspect extraction and rating classification of customer
tourists, and contribute to the country’s economic review data. New York: Springer International Publishing.
development. https://doi.org/10.1007/978-3-030-18590-9_13
Kim, M., Lee, S. M., Choi, S., & Kim, S. Y. (2021). Impact of visual
This study has presented two methods to rate hotels in information on online consumer review behavior: Evidence
Vietnam including overall rating and aspect rating. Both from a hotel booking website. Journal of Retailing and
methods have low errors and can be applied in rating Consumer Services, 60(2), 102494. https://doi.org/10.1016/
j.jretconser.2021.102494
Vietnamese hotels according to the trend of big data analysis
of guest reviews as other countries in the world follow. Kim, S. H., & Yoo, B. K. (2021). Topics and sentiment analysis
based on reviews of omnichannel retailing. Journal of
Distribution Science, 19(4), 25–35. https://doi.org/10.15722/
References jds.19.4.202104.25
Abrate, G., Quinton, S., & Pera, R. (2021). The relationship Lai, C. H., & Hsu, C. Y. (2021). Rating prediction is based on the
between price paid and hotel review ratings: Expectancy- combination of review mining and user preference analysis.
disconfirmation or placebo effect? Tourism Management, Information Systems, 99, 101742. https://doi.org/10.1016/
85(2), 104314. https://doi.org/10.1016/j.tourman.2021.104314 j.is.2021.101742
Akhtar, N., Zubair, N., Kumar, A., & Ahmad, T. (2017). Aspect- Le, Q. H., Nguyen, T. X. T., & Le, T. T. T. (2020). Customer
based sentiment-oriented summarization of hotel reviews. satisfaction in hotel services: A case study of Thanh Hoa
Procedia Computer Science, 115, 563–571. https://doi.org/ Province, Vietnam. Journal of Asian Finance, Economics, and
10.1016/j.procs.2017.09.115 Business, 7(10), 919–928. https://doi.org/10.13106/jafeb.2020.
Al-Natour, S., & Turetken, O. (2020). A comparative assessment vol7.no10.919
of sentiment analysis and star ratings for consumer reviews. Lee, J. W. (2020). Big data strategies for government, society, and
International Journal of Information Management, 54(4), policy-making. Journal of Asian Finance, Economics, and
102132. https://doi.org/10.1016/j.ijinfomgt.2020.102132 Business, 7(7), 475–487. https://doi.org/10.13106/jafeb.2020.
Bigné, E., William, E., & Soria-Olivas, E. (2020). Similarity vol7.no7.475
and consistency in hotel online ratings across platforms. Luo, Y., & Tang, R. (2019). Understanding hidden dimensions
Journal of Travel Research, 59(4), 742–758. https://doi.org/ in textual reviews on Airbnb: An application of modified
10.1177/0047287519859705 latent aspect rating analysis (LARA). International Journal
Chang, Y. C., Ku, C. H., & Chen, C. H. (2019). Social media of Hospitality Management, 80(1), 144–154. https://doi.
analytics: Extracting and visualizing Hilton hotel ratings org/10.1016/j.ijhm.2019.02.008
and reviews from TripAdvisor. International Journal of Manes, E., & Tchetchik, A. (2018). The role of electronic word
Information Management, 48(April 2017), 263–279. https:// of mouth in reducing information asymmetry: An empirical
doi.org/10.1016/j.ijinfomgt.2017.11.001 investigation of online hotel booking. Journal of Business
De Pelsmacker, P., van Tilburg, S., & Holthof, C. (2018). Digital Research, 85(12), 185–196. https://doi.org/10.1016/
marketing strategies, online reviews, and hotel performance. j.jbusres.2017.12.019
International Journal of Hospitality Management, 72(1), Margaris, D., & Vassilakis, C. (2018). Enhancing rating prediction
47–55. https://doi.org/10.1016/j.ijhm.2018.01.003 quality through improving the accuracy of detection of shifts
El-Said, O. A. (2020). Impact of online reviews on hotel booking in rating practices. Berlin Heidelberg: Springer. https://doi.
intention: The moderating role of brand image, star category, org/10.1007/978-3-662-57932-9_5
and price. Tourism Management Perspectives, 33(10), 100604. Masiero, L., & Nicolau, J. L. (2016). Choice behavior in online
https://doi.org/10.1016/j.tmp.2019.100604 hotel booking. Tourism Economics, 22(3), 671–678. https://doi.
Goeltom, V. A. H., Kristiana, Y., Juliana, J., Bernato, I., & org/10.5367/te.2015.0464
Pramono, R. (2020). The effect of service quality and value Park, Y. E., & Javed, Y. (2020). Insights discovery through hidden
of five-star hotel services on behavioral intentions with the sentiment in big data: Evidence from Saudi Arabia’s financialHa Thi Thu NGUYEN, Tuan Minh TRAN, Giang Binh NGUYEN / Journal of Asian Finance, Economics and Business Vol 8 No 8 (2021) 0443–0451 451
sector. Journal of Asian Finance, Economics, and Business, 7(6), Springer International Publishing. https://doi.org/10.1007/978-
457–464. https://doi.org/10.13106/jafeb.2020.vol7.no6.457 3-030-59082-6_6
Rhee, H. T., & Yang, S. B. (2015). Does the hotel attribute impor Wang, H., Lu, Y., & Zhai, C. (2010). A latent aspect rating
tance differ by the hotel? Focusing on hotel star classifications analysis on review text data. Proceedings of the 16th
and customers’ overall ratings. Computers in Human Behavior, ACM SIGKDD International Conference on Knowledge
50, 576–587. https://doi.org/10.1016/j.chb.2015.02.069 Discovery and Data Mining, Washington DC, 25–28 July
Sánchez-Lozano, G., Pereira, L. N., & Chávez-Miranda, E. 2010 (pp. 783–792). https://doi.org/10.1145/1835804.1835
(2021). Big data hedonic pricing: Econometric insights into 903783
room rates’ determinants by hotel category. Tourism Manage Wang., Sun, J., & Wen, H. (2019). Tourism seasonality, online
ment, 85(4). https://doi.org/10.1016/j.tourman.2021.104308 user rating and hotel price: A quantitative approach based on
Sharma, H., Tandon, A., & Aggarwal, A. G. (2020). Ranking hotels the hedonic price model. International Journal of Hospitality
based on online hotel attribute ratings using neutrosophic AHP Management, 79(12), 140–147. https://doi.org/10.1016/
and stochastic dominance. Singapore: Springer. https://doi.org/ j.ijhm.2019.01.007
10.1007/978-981-15-1420-3_94 Xue, W., Li, T., & Rishe, N. (2017). Aspect identification and
Sokhin, T., Khodorchenko, M., & Butakov, N. (2020). Unsupervised rating inference for hotel reviews. World Wide Web, 20(1),
neural aspect extraction with related terms. New York: 23–37. https://doi.org/10.1007/s11280-016-0398-9You can also read
